CN115273111B - Device for identifying drawing material sheet without template - Google Patents
Device for identifying drawing material sheet without template Download PDFInfo
- Publication number
- CN115273111B CN115273111B CN202210732579.5A CN202210732579A CN115273111B CN 115273111 B CN115273111 B CN 115273111B CN 202210732579 A CN202210732579 A CN 202210732579A CN 115273111 B CN115273111 B CN 115273111B
- Authority
- CN
- China
- Prior art keywords
- determining
- acquiring
- line
- characters
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 7
- 230000004807 localization Effects 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 17
- 238000010586 diagram Methods 0.000 description 11
- 230000009286 beneficial effect Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012015 optical character recognition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/412—Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
- G06V30/19013—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Character Input (AREA)
Abstract
The invention provides a device for identifying a drawing material sheet without a template, which comprises: acquiring a drawing, determining material table area information in the drawing, and generating a table picture; generating a horizontal and vertical pixel mean value curve according to the table picture; traversing the horizontal and vertical pixel mean curves to obtain table line position information; acquiring character information in the table line according to the table line position information; dividing the character information in the table line, and determining a corresponding table head row; processing characters in a material table based on the table head row to determine a table line; matching the header characters based on a preset header field, and determining the meaning of the header field according to a matching result; and acquiring a sequence number column in the material table, and merging the sequence rows according to the meaning of a header field. The method can automatically identify the content of the material table in the drawing without customizing the template, supports no table line, and has higher table identification efficiency and accuracy.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a device for recognizing a drawing material sheet without a template.
Background
At present, drawings are mainly made of paper or PDF, and the unstructured drawings cannot directly acquire and utilize the material list information on the drawings, so that a large amount of labor cost is needed to extract the materials into the electronic forms again. Automatic extraction of the material sheet by the computer will greatly provide the working efficiency.
The material table types may be divided into wireless tables and wired tables according to whether there is a table line or not. The existing general table identification technology can well identify wired tables, but is poor in wireless table identification.
In the prior art, different tables and different columns are distinguished by defining a template, specifying the position of the table in the drawing and specifying how to divide columns. The technology needs to define a template in advance, so that the real-time performance of the system is reduced, and the complexity of the system is improved. And cannot adapt to the situation that the position of the form in the drawing is not fixed.
Disclosure of Invention
The invention provides a method for identifying a wired form, which is used for solving the problems that the identification precision of the wireless form is not high and a template needs to be defined in advance and is suitable for identifying the wired form.
An apparatus for template-free identification of a drawing material sheet, comprising:
acquiring a drawing, and determining material table area information in the drawing;
generating a form picture according to the material table region information;
generating a horizontal and vertical pixel mean value curve according to the table picture;
traversing the horizontal and vertical pixel mean curves to acquire table line position information;
acquiring the in-line character information of the table according to the position information of the table line;
dividing the character information in the table line to obtain table head characters, and determining corresponding table head rows according to the table head characters;
processing characters in a material table based on the table head row to determine a table line;
matching the header characters based on a preset header field, determining a matching result, and determining the meaning of the header field according to the matching result;
and acquiring a sequence number column in the material table, merging the sequence rows according to the meaning of a table header field, and determining a merging result.
As an embodiment of the present invention: the acquiring of the drawing and the determining of the material sheet area information in the drawing comprise:
and uploading the drawing paper to a pre-trained table object detection neural network model, and determining the upper left corner point and the lower right corner point of the material table.
As an embodiment of the invention: the pre-trained table object detection neural network model is used for carrying out region positioning on a material table in a drawing.
As an embodiment of the present invention: generating a horizontal and vertical pixel mean value curve according to the table picture, comprising:
acquiring pixel values of each row in a table picture, calculating a pixel average value aiming at each row of pixels, and acquiring a transverse pixel average value curve corresponding to the table picture;
and acquiring each column of pixel values in the table picture, calculating a pixel average value aiming at each column of pixels, and acquiring a vertical pixel average value curve corresponding to the table picture.
As an embodiment of the present invention: the traversing is performed according to the horizontal and vertical pixel mean curves, obtaining table line position information, comprising:
and judging the pixel mean value corresponding to the horizontal and vertical pixel mean value curve corresponding to the table picture, and determining a judgment result.
As an embodiment of the present invention: the determining the pixel mean value corresponding to the horizontal and vertical pixel mean value curve corresponding to the table picture and determining the determination result includes:
when the pixel mean value is less than 10, judging that a solid-line table line exists in the table picture;
and when the pixel mean value is larger than 250, judging that a hidden table line exists in the table picture.
As an embodiment of the present invention: the dividing the table in-line character information to obtain the table head characters comprises the following steps:
matching each line of characters in the material table based on a preset table header field, and determining a matching rate;
and when the matching rate is more than 90%, determining that the characters are header characters.
As an embodiment of the invention: processing the characters in the material table based on the table head row to determine a table line, wherein the table line comprises:
acquiring a head position, and deleting the table lines and characters above the head position;
acquiring a table line covered on characters in the material table, and deleting the table line covered on the characters;
and acquiring the information of the remaining table lines in the material table, and determining the information of the remaining table lines as the table lines.
As an embodiment of the present invention: the acquiring sequence number columns in the material table, merging the sequence rows according to the meaning of the header fields, and determining a merging result includes:
checking a sequence number column in the material table, and determining whether an empty sequence number exists in the sequence number column;
and if the sequence number column has the empty sequence number, acquiring a row where the empty sequence number is located and a row above the row where the empty sequence number is located, merging the row where the empty sequence number is located and the row above the row where the empty sequence number is located, and determining a row merging result.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of an apparatus for template-free identification of a drawing material sheet according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an effect of a horizontal-vertical pixel mean value curve formed by connecting average values of pixels in each row or column of a material table in an apparatus for identifying a drawing material table without a template according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a result of generating a table line according to a horizontal-vertical pixel mean curve in a material table in an apparatus for template-free identification of a drawing material table according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating the process of determining header text in the apparatus for template-free identification of a drawing material sheet according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating the result of obtaining the ruled lines in an apparatus for identifying a drawing material sheet without a template according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
It is noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions, and that "plurality" means two or more than two unless expressly specified otherwise. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Example 1:
the embodiment of the invention provides a device for identifying a drawing material sheet without a template, which is shown in figure 1 and comprises the following components:
acquiring a drawing, and determining material sheet area information in the drawing;
generating a form picture according to the material table region information;
generating a horizontal and vertical pixel mean value curve according to the table picture;
traversing the horizontal and vertical pixel mean curves to acquire table line position information;
acquiring character information in the table line according to the table line position information;
dividing the character information in the table line to obtain table head characters, and determining corresponding table head rows according to the table head characters;
processing characters in a material table based on the table head row to determine a table line;
matching the header characters based on a preset header field, determining a matching result, and determining the meaning of the header field according to the matching result;
acquiring a sequence number column in a material table, merging sequence rows according to the meaning of a table header field, and determining a merging result;
the principle of this technical scheme implementation: in the technical scheme, a paper material table positioning model is trained, an object detection network for deep learning is used for training, such as a ppyolov2 object detection network, the trained network model is converted into a model for reasoning and a material table positioning model, area information of the material table, namely upper left corner positioning information and lower right corner positioning information, is determined, and a table picture is generated by intercepting the positioning information of the material table; calculating the pixel average value of each row of pixels of the table picture, and respectively obtaining the horizontal and vertical pixel average value curves of the table picture; traversing the horizontal and vertical pixel mean curves to obtain a solid line table line and an invisible table line, and sending the table picture into an optical character recognition system for character recognition to obtain character positions and information of the selected area; dividing the characters by a row table line, judging whether each row of characters is a header character, and if the header character exists, considering the row as a header row; deleting the table lines and characters above the head row, deleting the table lines covering the characters, and taking the rest table lines as determined table lines; and matching the header characters by using the collected header fields, determining the meaning of the current header fields in the matching process according to the meanings of the collected header fields, and merging the row with the empty sequence number in the sequence number column with the previous row according to the header meanings.
The beneficial effects of the above technical scheme are: the method and the device train through the deeply learned object detection network, which is favorable for improving the accuracy and the efficiency of material table identification, and the material table positioning model only needs to train once and can be used for multiple times subsequently, so that the utilization rate of the model is improved; by calculating the horizontal and vertical pixel mean curves of the table pictures, the difference between the horizontal and vertical table lines in the drawing material table and the background and characters can be obtained quickly, and the accuracy of finding out the table lines is improved; characters in the material table are identified through an optical character identification system, and the region position and information reliability of the obtained target characters are high, and the identification speed is high; therefore, the method can automatically identify the content of the material table in the drawing without customizing the template, supports no table line and has higher efficiency and accuracy of table identification.
Example 2:
the embodiment of the invention provides a device for identifying a drawing material sheet without a template, which comprises the following components: the acquiring of the drawing and the determining of the material sheet area information in the drawing comprise:
uploading the drawing to a pre-trained table object detection neural network model, and determining an upper left corner point and a lower right corner point of the material table;
the principle of this technical scheme implementation: the table object detection neural network model in the technical scheme is used for automatically determining the area where the material table in the drawing is located, when the drawing is collected, the model keeps the aspect ratio of the drawing and converts the width ratio of the drawing into a picture with the height of 2000 pixels, the material table area is marked on the drawing picture manually, and the object detection network with learned availability is trained. For example, the ppyolov2 object detection network converts the trained network model into a model for reasoning and a material table positioning model, and finally sends a drawing into the material table model to obtain the position corresponding to the material table;
the beneficial effects of the above technical scheme are: the neural network model for detecting the table object only needs to be trained once, and can be used for multiple times subsequently, so that the network use efficiency is improved, the identification time of the material table is saved, in addition, the network is trained through deep learning, the network adaptability is improved, the data processing speed is high, the accuracy is high, and the identification and the positioning of the table-free picture can be improved.
Example 3:
the embodiment of the invention provides a device for identifying a drawing material sheet without a template, which comprises the following components as shown in figure 2: generating a horizontal and vertical pixel mean value curve according to the table picture, comprising:
acquiring a pixel value of each row in the table picture, calculating a pixel average value aiming at each row of pixels, and acquiring a transverse pixel average value curve corresponding to the table picture;
acquiring each row of pixel values in the table picture, calculating a pixel average value aiming at each row of pixels, and acquiring a vertical pixel average value curve corresponding to the table picture;
the principle of this technical scheme implementation: in the technical scheme, the pixel average value of each row and each column is calculated by the table picture according to the pixels, in the figure 2, the right curve represents a horizontal pixel average value curve, and the bottom represents a vertical pixel average value curve;
the beneficial effects of the above technical scheme are: the device disclosed by the invention is favorable for acquiring the difference between the horizontal and vertical table lines of the material table and the background and characters by calculating the horizontal and vertical pixel mean curves of the material table, so that the wireless table and the wired table can be better identified, the practicability is stronger, and the condition that the positions of the tables in a drawing are not fixed can be well met.
Example 4:
the embodiment of the invention provides a device for identifying a drawing material sheet without a template, which comprises the following components: the step of judging the pixel mean value corresponding to the horizontal and vertical pixel mean value curve corresponding to the table picture and determining the judgment result comprises the following steps:
when the pixel mean value is less than 10, judging that a solid-line table line exists in the table picture;
when the pixel mean value is larger than 250, judging that a hidden table line exists in the table picture;
the principle of this technical scheme implementation: in the technical scheme, a horizontal and vertical pixel mean curve is traversed, and if the mean is less than 10, a solid line table line artificially exists. If the mean is greater than 250, then a hidden form line is deemed to exist, the lines drawn within the form of FIG. 3 representing possible form lines;
the beneficial effects of the above technical scheme are: according to the method and the device, the possible table lines are determined by judging the mean values corresponding to the horizontal and vertical pixel mean value curves, and the subsequent judgment based on the possible table lines is facilitated, so that the accuracy of the table lines is improved, and the identification efficiency of the material table is improved.
Example 5:
the embodiment of the invention provides a device for identifying a drawing material sheet without a template, which comprises the following components as shown in figure 4: the dividing the table in-line character information to obtain the table head characters comprises the following steps:
matching each line of characters in the material table based on a preset table header field, and determining a matching rate;
when the matching rate is greater than 90%, determining that the characters are header characters;
the principle of this technical scheme implementation: in the technical scheme, the characters are divided into lines by using line table lines, whether each line of characters is a header character is judged in sequence, if the header characters exist, the line is considered as a header line, the header characters are judged by utilizing all collected header fields for matching, if the matching rate is more than 90%, the header characters are considered, and the specific judgment flow is shown in figure 4;
the beneficial effects of the above technical scheme are: the method and the device aim at possible table lines as target processing objects, determine the table header characters by matching the existing table header fields, and the accuracy of the table header characters determined in the mode is higher, so that the method and the device are beneficial to improving the accuracy of the table lines and increasing the identification efficiency of the material table.
Example 6:
the embodiment of the invention provides a device for identifying a drawing material sheet without a template, which comprises the following components as shown in figure 5: processing the characters in the material table based on the table head row to determine a table line, wherein the table line comprises:
acquiring a head position, and deleting the table lines and characters above the head position;
acquiring a table line covered on characters in the material table, and deleting the table line covered on the characters;
acquiring residual table line information in a material table, and determining the residual table line information as table lines;
the principle of this technical scheme implementation: in the technical scheme, the table lines and characters above the head are deleted, the table lines covering the characters are deleted, and the remaining table lines are determined table lines;
the beneficial effects of the above technical scheme are: the method takes the possible table lines as target processing objects, deletes the invalid parts in the possible table lines, and the remaining table lines are the determined table lines.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. An apparatus for template-free identification of a drawing sheet of material, comprising:
acquiring a drawing, and determining material sheet area information in the drawing;
generating a form picture according to the material table region information;
generating a horizontal and vertical pixel mean curve according to the table picture;
traversing the horizontal and vertical pixel mean curves to acquire table line position information;
acquiring the in-line character information of the table according to the position information of the table line;
dividing the character information in the table line to obtain table head characters, and determining corresponding table head rows according to the table head characters;
processing characters in a material table based on the table head row to determine a table line;
matching the header characters based on a preset header field, determining a matching result, and determining the meaning of the header field according to the matching result;
acquiring a sequence number column in a material table, merging sequence rows according to the meaning of a table header field, and determining a merging result;
wherein, according to the table picture, generating a horizontal and vertical pixel mean value curve comprises:
acquiring pixel values of each row in a table picture, calculating a pixel average value aiming at each row of pixels, and acquiring a transverse pixel average value curve corresponding to the table picture;
and acquiring each column of pixel values in the table picture, calculating a pixel average value aiming at each column of pixels, and acquiring a vertical pixel average value curve corresponding to the table picture.
2. The apparatus of claim 1, wherein the obtaining the drawing and determining the material table region information in the drawing comprises:
and uploading the graph paper to a pre-trained table object detection neural network model, and determining the upper left corner point and the lower right corner point of the material table.
3. The apparatus of claim 2, in which the pre-trained form object detection neural network model is used for region localization for a sheet of material within a drawing.
4. The apparatus of claim 1, wherein said traversing for the horizontal and vertical pixel mean curves to obtain table line position information comprises:
and judging the pixel mean value corresponding to the horizontal and vertical pixel mean value curve corresponding to the table picture, and determining a judgment result.
5. The apparatus of claim 4, wherein the determining the pixel mean value corresponding to the horizontal and vertical pixel mean value curves corresponding to the table picture and determining the determination result comprises:
when the pixel mean value is less than 10, judging that a solid-line table line exists in the table picture;
and when the pixel mean value is larger than 250, judging that a hidden table line exists in the table picture.
6. The apparatus of claim 1, wherein the dividing the table inline text information to obtain the header text comprises:
matching each line of characters in the material table based on a preset table header field, and determining a matching rate;
and when the matching rate is greater than 90%, determining that the characters are header characters.
7. The apparatus of claim 1, wherein said processing words in a material table based on said header row to determine a form line comprises:
acquiring a head position, and deleting the table lines and characters above the head position;
acquiring a table line covered on characters in the material table, and deleting the table line covered on the characters;
and acquiring the information of the remaining table lines in the material table, and determining the information of the remaining table lines as the table lines.
8. The apparatus of claim 1, wherein the obtaining sequence number columns in the material table and merging sequence rows according to the meaning of the header field, and determining a merging result comprises:
checking a sequence number column in the material table, and determining whether an empty sequence number exists in the sequence number column;
and if the sequence number column has the empty sequence number, acquiring a row where the empty sequence number is located and a row above the row where the empty sequence number is located, merging the row where the empty sequence number is located and the row above the row where the empty sequence number is located, and determining a row merging result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210732579.5A CN115273111B (en) | 2022-06-27 | 2022-06-27 | Device for identifying drawing material sheet without template |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210732579.5A CN115273111B (en) | 2022-06-27 | 2022-06-27 | Device for identifying drawing material sheet without template |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115273111A CN115273111A (en) | 2022-11-01 |
| CN115273111B true CN115273111B (en) | 2023-04-18 |
Family
ID=83762459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210732579.5A Active CN115273111B (en) | 2022-06-27 | 2022-06-27 | Device for identifying drawing material sheet without template |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115273111B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133621B (en) * | 2017-05-12 | 2020-09-29 | 中电鸿信信息科技有限公司 | Method for classifying and extracting information of formatted fax based on OCR |
| CN109086756B (en) * | 2018-06-15 | 2021-08-03 | 众安信息技术服务有限公司 | Text detection analysis method, device and equipment based on deep neural network |
| CN110163198B (en) * | 2018-09-27 | 2022-03-08 | 腾讯科技（深圳）有限公司 | Table identification reconstruction method and device and storage medium |
| CN113408323B (en) * | 2020-03-17 | 2023-03-03 | 华为技术有限公司 | Extraction method, device and equipment of table information and storage medium |
| CN111695553B (en) * | 2020-06-05 | 2023-09-08 | 北京百度网讯科技有限公司 | Form identification method, device, equipment and medium |
| CN113297975B (en) * | 2021-05-25 | 2024-03-26 | 新东方教育科技集团有限公司 | Table structure identification method and device, storage medium and electronic equipment |
| CN113487702A (en) * | 2021-07-05 | 2021-10-08 | 上海商汤临港智能科技有限公司 | Template generation method, image recognition method and device |
| CN113962201A (en) * | 2021-08-24 | 2022-01-21 | 重庆超体科技有限公司 | Document structuralization and extraction method for documents |
| CN113901768A (en) * | 2021-09-30 | 2022-01-07 | 平安国际智慧城市科技股份有限公司 | Standard file generation method, device, equipment and storage medium |
-
2022
- 2022-06-27 CN CN202210732579.5A patent/CN115273111B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115273111A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103824053B (en) | The sex mask method and face gender detection method of a kind of facial image | |
| CN103955660B (en) | Method for recognizing batch two-dimension code images | |
| CN109858476B (en) | Tag expansion method and electronic equipment | |
| CN104298982A (en) | Text recognition method and device | |
| CN108805076A (en) | The extracting method and system of environmental impact assessment report table word | |
| CN110598566A (en) | Image processing method, device, terminal and computer readable storage medium | |
| CN111695540A (en) | Video frame identification method, video frame cutting device, electronic equipment and medium | |
| CN112446262A (en) | Text analysis method, text analysis device, text analysis terminal and computer-readable storage medium | |
| CN112307919B (en) | Improved YOLOv 3-based digital information area identification method in document image | |
| CN111275040A (en) | Positioning method and device, electronic equipment and computer readable storage medium | |
| CN111753642B (en) | Method and device for determining key frame | |
| CN111652141B (en) | Question segmentation method, device, equipment and medium based on question numbers and text lines | |
| CN111652140A (en) | Method, device, equipment and medium for accurately segmenting questions based on deep learning | |
| CN114140665A (en) | Dense small target detection method based on improved YOLOv5 | |
| CN113762274B (en) | Answer sheet target area detection method, system, storage medium and equipment | |
| CN111488847A (en) | System, method and terminal for acquiring sports game video goal segment | |
| CN103699876A (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images | |
| CN114386504A (en) | Engineering drawing character recognition method | |
| CN111144270A (en) | Evaluation method and evaluation device for handwritten text neatness based on neural network | |
| CN115273111B (en) | Device for identifying drawing material sheet without template | |
| CN116596921B (en) | Method and system for sorting incinerator slag | |
| CN111047614B (en) | Feature extraction-based method for extracting target corner of complex scene image | |
| CN114565749A (en) | Method and system for identifying key content of visa document of power construction site | |
| CN115050025A (en) | Knowledge point extraction method and device based on formula recognition | |
| CN110276260B (en) | Commodity detection method based on depth camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A device for template free recognition of drawing material lists Granted publication date: 20230418 Pledgee: Bank of Nanjing Limited by Share Ltd. Beijing branch Pledgor: Beijing mutual time Technology Co.,Ltd. Registration number: Y2024980014268 |